Multi-Frame Example-Based Super-Resolution Using Locally Directional Self-Similarity
Abstract-This project presents a multi-frame super resolution approach to reconstruct a high-resolution image from several low-resolution video frames. The proposed algorithm consists of three steps: i) definition of a local search region for the optimal patch using motion vectors, ii) adaptive selection of the optimum patch based on low resolution image degradation model, and iii) combination of the optimum patch and reconstructed image. As a result, the proposed algorithm can remove interpolation artifacts using directionally adaptive patch selection based on the low resolution
image degradation model. Moreover, super resolved images without distortion between consecutive
frames can be generated. The proposed method provides a significantly improved super-resolution performance over existing methods in the sense of both subjective and objective measures including peak-to-peak signal-to-noise ratio (PSNR), structural similarity measure (SSIM), and naturalness image quality evaluator (NIQE). The proposed multi-frame super-resolution algorithm is designed for realtime video processing hardware by reducing the search region for optimal patches, and suitable for consumer imaging devices including ultra-high-definition (UHD) digital televisions, surveillance systems, and medical imaging systems for image restoration and enhancement.
image degradation model. Moreover, super resolved images without distortion between consecutive
frames can be generated. The proposed method provides a significantly improved super-resolution performance over existing methods in the sense of both subjective and objective measures including peak-to-peak signal-to-noise ratio (PSNR), structural similarity measure (SSIM), and naturalness image quality evaluator (NIQE). The proposed multi-frame super-resolution algorithm is designed for realtime video processing hardware by reducing the search region for optimal patches, and suitable for consumer imaging devices including ultra-high-definition (UHD) digital televisions, surveillance systems, and medical imaging systems for image restoration and enhancement.
Block diagram of the proposed SR algorithm.
The proposed SR algorithm consists of three steps: i) definition of a local search region for the optimal patch using motion vectors, ii) adaptive selection of the optimum patch based on low-resolution image degradation model, and iii) combination of the optimum patch and reconstructed image.
Motion estimation process for local region definition
To reduce the computational complexity in multiframe SR, the proposed method resolves by using motion information to confine the patch searching region as small as possible. The local search region is also defined using pre-generated down-scaled images for fast motion vector estimation.
Generation of LR and HR patch pairs using the image degradation model.
Simulation Video Demo
No comments:
Post a Comment